Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    notes about pets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ZL
    0.45
     मानदंडों
    0.43
    邯
    0.43
     Productivity
    0.43
     iPad
    0.41
    Pods
    0.41
    lw
    0.41
     डो
    0.41
     Ն
    0.40
    一方
    0.40
    POSITIVE LOGITS
     certes
    0.46
    ர்
    0.45
    emment
    0.44
     بهتر
    0.44
    اموش
    0.43
    ার
    0.43
    varande
    0.42
    ழ்ச்ச
    0.42
     التالية
    0.41
     හොඳ
    0.41
    Act Density 0.002%

    No Known Activations